Benchmark
MMAU-Pro IF
Scores are percentages.
- Models measured
- 9
- Scores recorded
- 9
- Sources
- 1
- IQ weight
- 1.26
Score distribution
- 71.5%
- Mean
- 75.9%
- Median
- 24%
- Std dev
- 36.4%
- 10th percentile
- 94.2%
- 90th percentile
- 29.6%
- Min
This benchmark has a weight of 1.26 for chat models, measured over 8 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Flash· MMAU-Pro data | 95.1% |
| 2 | Gemini 2.0 Flash· MMAU-Pro data | 94.2% |
| 3 | Gemini 3.6 Flash· MMAU-Pro data | 93.1% |
| 4 | Gemini 3.7 Flash· MMAU-Pro data | 93.1% |
| 5 | Gemini 3.5 Flash· MMAU-Pro data | 75.9% |
| 6 | Gemini 3.1 Pro Preview· MMAU-Pro data | 64.4% |
| 7 | Qwen2.5-Omni 7B· MMAU-Pro data | 61.3% |
| 8 | Gemma 3n E4B IT· MMAU-Pro data | 36.4% |
| 9 | Gemma 3n E2b It· MMAU-Pro data | 29.6% |